Merge tag 'mm-hotfixes-stable-2023-07-28-15-52' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull hotfixes from Andrew Morton:
 "11 hotfixes. Five are cc:stable and the remainder address post-6.4
  issues or aren't considered serious enough to justify backporting"

* tag 'mm-hotfixes-stable-2023-07-28-15-52' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/memory-failure: fix hardware poison check in unpoison_memory()
  proc/vmcore: fix signedness bug in read_from_oldmem()
  mailmap: update remaining active codeaurora.org email addresses
  mm: lock VMA in dup_anon_vma() before setting ->anon_vma
  mm: fix memory ordering for mm_lock_seq and vm_lock_seq
  scripts/spelling.txt: remove 'thead' as a typo
  mm/pagewalk: fix EFI_PGT_DUMP of espfix area
  shmem: minor fixes to splice-read implementation
  tmpfs: fix Documentation of noswap and huge mount options
  Revert "um: Use swap() to make code cleaner"
  mm/damon/core-test: initialise context before test in damon_test_set_attrs()

Author: torvalds

.mailmap

@@ -84,8 +84,6 @@ nr_inodes  The maximum number of inodes for this instance. The default
            is half of the number of your physical RAM pages, or (on a
            machine with highmem) the number of lowmem RAM pages,
            whichever is the lower.
-noswap     Disables swap. Remounts must respect the original settings.
-           By default swap is enabled.
 =========  ============================================================
 
 These parameters accept a suffix k, m or g for kilo, mega and giga and
@@ -99,36 +97,31 @@ mount with such options, since it allows any user with write access to
 use up all the memory on the machine; but enhances the scalability of
 that instance in a system with many CPUs making intensive use of it.
 
+tmpfs blocks may be swapped out, when there is a shortage of memory.
+tmpfs has a mount option to disable its use of swap:
+
+======  ===========================================================
+noswap  Disables swap. Remounts must respect the original settings.
+        By default swap is enabled.
+======  ===========================================================
+
 tmpfs also supports Transparent Huge Pages which requires a kernel
 configured with CONFIG_TRANSPARENT_HUGEPAGE and with huge supported for
 your system (has_transparent_hugepage(), which is architecture specific).
 The mount options for this are:
 
-======  ============================================================
-huge=0  never: disables huge pages for the mount
-huge=1  always: enables huge pages for the mount
-huge=2  within_size: only allocate huge pages if the page will be
-        fully within i_size, also respect fadvise()/madvise() hints.
-huge=3  advise: only allocate huge pages if requested with
-        fadvise()/madvise()
-======  ============================================================
-
-There is a sysfs file which you can also use to control system wide THP
-configuration for all tmpfs mounts, the file is:
-
-/sys/kernel/mm/transparent_hugepage/shmem_enabled
-
-This sysfs file is placed on top of THP sysfs directory and so is registered
-by THP code. It is however only used to control all tmpfs mounts with one
-single knob. Since it controls all tmpfs mounts it should only be used either
-for emergency or testing purposes. The values you can set for shmem_enabled are:
-
-==  ============================================================
--1  deny: disables huge on shm_mnt and all mounts, for
-    emergency use
--2  force: enables huge on shm_mnt and all mounts, w/o needing
-    option, for testing
-==  ============================================================
+================ ==============================================================
+huge=never       Do not allocate huge pages.  This is the default.
+huge=always      Attempt to allocate huge page every time a new page is needed.
+huge=within_size Only allocate huge page if it will be fully within i_size.
+                 Also respect madvise(2) hints.
+huge=advise      Only allocate huge page if requested with madvise(2).
+================ ==============================================================
+
+See also Documentation/admin-guide/mm/transhuge.rst, which describes the
+sysfs file /sys/kernel/mm/transparent_hugepage/shmem_enabled: which can
+be used to deny huge pages on all tmpfs mounts in an emergency, or to
+force huge pages on all tmpfs mounts for testing.
 
 tmpfs has a mount option to set the NUMA memory allocation policy for
 all files in that instance (if CONFIG_NUMA is enabled) - which can be

Documentation/filesystems/tmpfs.rst

@@ -3,7 +3,6 @@
  * Copyright (C) 2002 - 2008 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  */
 
-#include <linux/minmax.h>
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
@@ -51,7 +50,7 @@ static struct pollfds all_sigio_fds;
 
 static int write_sigio_thread(void *unused)
 {
-	struct pollfds *fds;
+	struct pollfds *fds, tmp;
 	struct pollfd *p;
 	int i, n, respond_fd;
 	char c;
@@ -78,7 +77,9 @@ static int write_sigio_thread(void *unused)
 					       "write_sigio_thread : "
 					       "read on socket failed, "
 					       "err = %d\n", errno);
-				swap(current_poll, next_poll);
+				tmp = current_poll;
+				current_poll = next_poll;
+				next_poll = tmp;
 				respond_fd = sigio_private[1];
 			}
 			else {

arch/um/os-Linux/sigio.c

@@ -132,7 +132,7 @@ ssize_t read_from_oldmem(struct iov_iter *iter, size_t count,
 			 u64 *ppos, bool encrypted)
 {
 	unsigned long pfn, offset;
-	size_t nr_bytes;
+	ssize_t nr_bytes;
 	ssize_t read = 0, tmp;
 	int idx;
 

fs/proc/vmcore.c

@@ -641,8 +641,14 @@ static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
  */
 static inline bool vma_start_read(struct vm_area_struct *vma)
 {
-	/* Check before locking. A race might cause false locked result. */
-	if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))
+	/*
+	 * Check before locking. A race might cause false locked result.
+	 * We can use READ_ONCE() for the mm_lock_seq here, and don't need
+	 * ACQUIRE semantics, because this is just a lockless check whose result
+	 * we don't rely on for anything - the mm_lock_seq read against which we
+	 * need ordering is below.
+	 */
+	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq))
 		return false;
 
 	if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
@@ -653,8 +659,13 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
 	 * False unlocked result is impossible because we modify and check
 	 * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq
 	 * modification invalidates all existing locks.
+	 *
+	 * We must use ACQUIRE semantics for the mm_lock_seq so that if we are
+	 * racing with vma_end_write_all(), we only start reading from the VMA
+	 * after it has been unlocked.
+	 * This pairs with RELEASE semantics in vma_end_write_all().
 	 */
-	if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) {
+	if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) {
 		up_read(&vma->vm_lock->lock);
 		return false;
 	}
@@ -676,7 +687,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
 	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
 	 * mm->mm_lock_seq can't be concurrently modified.
 	 */
-	*mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
+	*mm_lock_seq = vma->vm_mm->mm_lock_seq;
 	return (vma->vm_lock_seq == *mm_lock_seq);
 }
 
@@ -688,7 +699,13 @@ static inline void vma_start_write(struct vm_area_struct *vma)
 		return;
 
 	down_write(&vma->vm_lock->lock);
-	vma->vm_lock_seq = mm_lock_seq;
+	/*
+	 * We should use WRITE_ONCE() here because we can have concurrent reads
+	 * from the early lockless pessimistic check in vma_start_read().
+	 * We don't really care about the correctness of that early check, but
+	 * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
+	 */
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
 	up_write(&vma->vm_lock->lock);
 }
 
@@ -702,7 +719,7 @@ static inline bool vma_try_start_write(struct vm_area_struct *vma)
 	if (!down_write_trylock(&vma->vm_lock->lock))
 		return false;
 
-	vma->vm_lock_seq = mm_lock_seq;
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
 	up_write(&vma->vm_lock->lock);
 	return true;
 }

include/linux/mm.h

@@ -514,6 +514,20 @@ struct vm_area_struct {
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
+	/*
+	 * Can only be written (using WRITE_ONCE()) while holding both:
+	 *  - mmap_lock (in write mode)
+	 *  - vm_lock->lock (in write mode)
+	 * Can be read reliably while holding one of:
+	 *  - mmap_lock (in read or write mode)
+	 *  - vm_lock->lock (in read or write mode)
+	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
+	 * while holding nothing (except RCU to keep the VMA struct allocated).
+	 *
+	 * This sequence counter is explicitly allowed to overflow; sequence
+	 * counter reuse can only lead to occasional unnecessary use of the
+	 * slowpath.
+	 */
 	int vm_lock_seq;
 	struct vma_lock *vm_lock;
 
@@ -679,6 +693,20 @@ struct mm_struct {
 					  * by mmlist_lock
 					  */
 #ifdef CONFIG_PER_VMA_LOCK
+		/*
+		 * This field has lock-like semantics, meaning it is sometimes
+		 * accessed with ACQUIRE/RELEASE semantics.
+		 * Roughly speaking, incrementing the sequence number is
+		 * equivalent to releasing locks on VMAs; reading the sequence
+		 * number can be part of taking a read lock on a VMA.
+		 *
+		 * Can be modified under write mmap_lock using RELEASE
+		 * semantics.
+		 * Can be read with no other protection when holding write
+		 * mmap_lock.
+		 * Can be read with ACQUIRE semantics if not holding write
+		 * mmap_lock.
+		 */
 		int mm_lock_seq;
 #endif
 

include/linux/mm_types.h

@@ -76,8 +76,14 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
 static inline void vma_end_write_all(struct mm_struct *mm)
 {
 	mmap_assert_write_locked(mm);
-	/* No races during update due to exclusive mmap_lock being held */
-	WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+	/*
+	 * Nobody can concurrently modify mm->mm_lock_seq due to exclusive
+	 * mmap_lock being held.
+	 * We need RELEASE semantics here to ensure that preceding stores into
+	 * the VMA take effect before we unlock it with this store.
+	 * Pairs with ACQUIRE semantics in vma_start_read().
+	 */
+	smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
 }
 #else
 static inline void vma_end_write_all(struct mm_struct *mm) {}

include/linux/mmap_lock.h

@@ -320,25 +320,25 @@ static void damon_test_update_monitoring_result(struct kunit *test)
 
 static void damon_test_set_attrs(struct kunit *test)
 {
-	struct damon_ctx ctx;
+	struct damon_ctx *c = damon_new_ctx();
 	struct damon_attrs valid_attrs = {
 		.min_nr_regions = 10, .max_nr_regions = 1000,
 		.sample_interval = 5000, .aggr_interval = 100000,};
 	struct damon_attrs invalid_attrs;
 
-	KUNIT_EXPECT_EQ(test, damon_set_attrs(&ctx, &valid_attrs), 0);
+	KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &valid_attrs), 0);
 
 	invalid_attrs = valid_attrs;
 	invalid_attrs.min_nr_regions = 1;
-	KUNIT_EXPECT_EQ(test, damon_set_attrs(&ctx, &invalid_attrs), -EINVAL);
+	KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &invalid_attrs), -EINVAL);
 
 	invalid_attrs = valid_attrs;
 	invalid_attrs.max_nr_regions = 9;
-	KUNIT_EXPECT_EQ(test, damon_set_attrs(&ctx, &invalid_attrs), -EINVAL);
+	KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &invalid_attrs), -EINVAL);
 
 	invalid_attrs = valid_attrs;
 	invalid_attrs.aggr_interval = 4999;
-	KUNIT_EXPECT_EQ(test, damon_set_attrs(&ctx, &invalid_attrs), -EINVAL);
+	KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &invalid_attrs), -EINVAL);
 }
 
 static struct kunit_case damon_test_cases[] = {

mm/damon/core-test.h

@@ -2487,7 +2487,7 @@ int unpoison_memory(unsigned long pfn)
 		goto unlock_mutex;
 	}
 
-	if (!folio_test_hwpoison(folio)) {
+	if (!PageHWPoison(p)) {
 		unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
 				 pfn, &unpoison_rs);
 		goto unlock_mutex;

mm/memory-failure.c

@@ -615,6 +615,7 @@ static inline int dup_anon_vma(struct vm_area_struct *dst,
 	 * anon pages imported.
 	 */
 	if (src->anon_vma && !dst->anon_vma) {
+		vma_start_write(dst);
 		dst->anon_vma = src->anon_vma;
 		return anon_vma_clone(dst, src);
 	}